| CPC G06F 12/0891 (2013.01) [G06F 12/0882 (2013.01); G06F 12/123 (2013.01)] | 19 Claims |
|
1. A method of improving performance and efficiency of storage systems deployed at disaster recovery (DR) sites, comprising:
receiving, at a destination node of a DR site from a source node at a production site, a large transfer of replication data including accumulated changes made to data of a production volume stored at the production site since a most recent synchronization of the production volume to a replica volume stored at the DR site in an asynchronous replication process, wherein any replication data stored in the replica volume at the DR site is written more frequently than the replication data is read;
partitioning the large transfer of replication data into a plurality of small write requests directed toward the replica volume stored at the DR site;
tagging each small write request of the plurality of small write requests with multiple tags to obtain a plurality of multi-tagged small write requests, the multiple tags including a first tag indicating a target type of a write target of the small write request, a second tag identifying the production site where the production volume is stored, and a third tag containing hint information pertaining to a data retention period of the replication data stored at the DR site, the write target of the small write request being the replica volume at the DR site, the target type of the write target being the replica volume at the DR site of the production volume at the production site; and
in response to servicing the plurality of multi-tagged small write requests, performing at least one of:
stream separation on the plurality of multi-tagged small write requests, the production site being a specific production site, the stream separation being performed based on the target type of the write target being the replica of the production volume as indicated by the first tag, and the production site being the specific production site as identified by the second tag; and
flushing the replication data stored in the replica volume at the DR site having an identical data retention period to a specific region of physical storage space for the replica volume, the flushing of the replication data being performed based on the target type of the write target being the replica at the DR site of the production volume at the production site as indicated by the first tag, and the hint information pertaining to the data retention period of the replication data stored at the DR site as contained in the third tag.
|